CN103268573B - A kind of wind energy turbine set mark post ventilator selection method based on principal component analysis (PCA) - Google Patents
A kind of wind energy turbine set mark post ventilator selection method based on principal component analysis (PCA) Download PDFInfo
- Publication number
- CN103268573B CN103268573B CN201310168790.XA CN201310168790A CN103268573B CN 103268573 B CN103268573 B CN 103268573B CN 201310168790 A CN201310168790 A CN 201310168790A CN 103268573 B CN103268573 B CN 103268573B
- Authority
- CN
- China
- Prior art keywords
- matrix
- mark post
- wind energy
- major component
- blower fan
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
- 238000000513 principal component analysis Methods 0.000 title claims abstract description 37
- 238000010187 selection method Methods 0.000 title claims abstract description 16
- 239000011159 matrix material Substances 0.000 claims abstract description 42
- 238000000034 method Methods 0.000 claims description 5
- 230000007547 defect Effects 0.000 abstract description 2
- 238000004141 dimensional analysis Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 240000004272 Eragrostis cilianensis Species 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005684 electric field Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
Landscapes
- Wind Motors (AREA)
Abstract
The invention discloses a kind of wind energy turbine set mark post ventilator selection method based on principal component analysis (PCA), comprise the history power curve obtaining every Fans in wind energy turbine set; History based on Fans every in wind energy turbine set is exerted oneself, set up blower fan and to exert oneself matrix
; Blower fan is exerted oneself matrix
after pre-service, principal component analysis (PCA) is carried out to it; To the foundation of major component as mark post ventilator selection of class discrimination degree be had, carry out mark post ventilator selection.Wind energy turbine set mark post ventilator selection method based on principal component analysis (PCA) of the present invention, can overcome the defects such as the low and Selection effect of efficiency of selection in prior art difference, to realize the advantage that efficiency of selection is high and Selection effect is good.
Description
Technical field
The present invention relates to technical field of wind power generation, particularly, relate to a kind of wind energy turbine set mark post ventilator selection method based on principal component analysis (PCA).
Background technology
For the theory of adding up wind energy turbine set is exerted oneself, generally need wind energy turbine set to select mark post blower fan, when limit is exerted oneself, should ensure that mark post blower fan is not limit as far as possible and exert oneself, therefore just occur this brand-new problem of mark post ventilator selection of how to carry out wind energy turbine set.The selection of mark post blower fan is representative, can characterize the overall operation situation of wind energy turbine set, objectively responds the year situation such as theoretical generated energy of this wind energy turbine set.
At present, because China ten million multikilowatt wind power base is still in the construction period, therefore not yet form complete effective wind energy turbine set mark post ventilator selection standard.
Realizing in process of the present invention, inventor finds the correlative study or the technology that do not occur wind energy turbine set mark post ventilator selection method at present.
Summary of the invention
The object of the invention is to, for the problems referred to above, propose a kind of wind energy turbine set mark post ventilator selection method based on principal component analysis (PCA), to realize the advantage that efficiency of selection is high and Selection effect is good.
For achieving the above object, the technical solution used in the present invention is: a kind of wind energy turbine set mark post ventilator selection method based on principal component analysis (PCA), comprising:
The history power curve of every typhoon electric fan in a, acquisition wind energy turbine set;
B, history power curve based on typhoon electric fan every in wind energy turbine set, set up blower fan and to exert oneself matrix
:
（1）；
M is wind energy turbine set inner blower number of units, and n is the power sample number of every Fans,
represent actual the exerting oneself of the i-th Fans, a jth moment point;
C, matrix that blower fan exerted oneself
carry out the process of square graduation, principal component analysis (PCA) is carried out to the matrix after the process of square graduation;
D, will the foundation of major component as mark post ventilator selection of class discrimination degree be had, carry out mark post ventilator selection.
Further, described step c specifically comprises:
C1, data prediction, by matrix
deduct Mean Matrix and be processed into the flat matrix of square
:
，
Wherein,
;
C2, based on above-mentioned data prediction result, carry out covariance calculating, obtain real symmetric matrix
:
,
for
turn order;
C3, realistic symmetrical matrix
proper vector
and eigenwert
, meet
, wherein
（
）（3），
Matrix
orthogonal matrix, matrix
?
column element is exactly eigenwert
characteristic of correspondence vector;
C4, according to above-mentioned real symmetric matrix
proper vector
and eigenwert
, obtain the variance contribution ratio of each proper vector and the accumulative variance contribution ratio of front several proper vector, obtain the major component describing power of fan.
Further, in step c4, the operation of the major component of described calculating wind energy turbine set, specifically comprises:
Get the individual larger eigenwert of front p that accumulative variance contribution ratio reaches 85-95%
corresponding first, second ...,
individual proper vector is major component;
The variance contribution ratio of each proper vector is defined as:
（4）；
The accumulative variance contribution ratio of a front p proper vector is defined as:
（5）。
Further, described steps d specifically comprises:
Descending by eigenwert, select the major component with class discrimination degree successively, in each classification of major component with class discrimination degree, select corresponding blower fan as mark post blower fan.
Further, described descending by eigenwert, select the major component with class discrimination degree successively, in each classification of major component with class discrimination degree, select corresponding blower fan as the operation of mark post blower fan, specifically comprise:
Descending by eigenwert, check the class discrimination degree of each major component successively;
If each component of a certain major component presents good class discrimination degree, then 1-2 Fans should be selected in each classification as the mark post blower fan of this wind energy turbine set;
See Fig. 2, for second major component that bag energy time is many, each blower fan shows different numerical value, mark post blower fans should be divided by two components, zero is greater than for major component component, be less than zero-sum close to zero blower fan 1-2 platform all should be selected as mark post blower fan.
The wind energy turbine set mark post ventilator selection method based on principal component analysis (PCA) of various embodiments of the present invention, owing to comprising the history power curve obtaining every Fans in wind energy turbine set; History based on Fans every in wind energy turbine set is exerted oneself, and sets up blower fan and to exert oneself matrix
; Blower fan is exerted oneself matrix
after pre-service, principal component analysis (PCA) is carried out to it; To the foundation of major component as mark post ventilator selection of class discrimination degree be had, carry out mark post ventilator selection; By falling dimensional analysis to the operate power data of each blower fan of wind energy turbine set in ten million multikilowatt wind power base, the representational mark post blower fan of most can be obtained; Thus the defect of the low and Selection effect difference of efficiency of selection in prior art can be overcome, to realize the advantage that efficiency of selection is high and Selection effect is good.
Other features and advantages of the present invention will be set forth in the following description, and, partly become apparent from instructions, or understand by implementing the present invention.
Below by drawings and Examples, technical scheme of the present invention is described in further detail.
Accompanying drawing explanation
Accompanying drawing is used to provide a further understanding of the present invention, and forms a part for instructions, together with embodiments of the present invention for explaining the present invention, is not construed as limiting the invention.In the accompanying drawings:
Fig. 1 is the schematic flow sheet of the wind energy turbine set mark post ventilator selection method that the present invention is based on principal component analysis (PCA);
Fig. 2 is the EOF decomposition result schematic diagram of first three proper vector in the wind energy turbine set mark post ventilator selection method that the present invention is based on principal component analysis (PCA).
Embodiment
Below in conjunction with accompanying drawing, the preferred embodiments of the present invention are described, should be appreciated that preferred embodiment described herein is only for instruction and explanation of the present invention, is not intended to limit the present invention.
For problems of the prior art, according to the embodiment of the present invention, as depicted in figs. 1 and 2, propose a kind of based on principal component analysis (PCA) (PCA, or claim empirical orthogonal to decompose, i.e. EOF) wind energy turbine set mark post ventilator selection method, by falling dimensional analysis to the operate power data of each blower fan of wind energy turbine set in ten million multikilowatt wind power base, the representational mark post blower fan of most can be obtained.
See Fig. 1, the wind energy turbine set mark post ventilator selection method based on principal component analysis (PCA) of the present embodiment, specifically comprises the following steps:
Step 1: the history power curve obtaining every typhoon electric fan in wind energy turbine set, advise every 5 minutes time points, time span was more than 6 months.
Step 2: establish in wind energy turbine set and have m Fans, every Fans has n power sample, then the blower fan that can form m capable n row is exerted oneself matrix
:
（1）；
represent the i-th Fans, actual the exerting oneself of a jth moment point.
Step 3: data prediction, by matrix
deduct Mean Matrix and be processed into the flat matrix of square
:
；
Wherein:
。
Step 4: calculate covariance matrix:
；
(
for
turn order) from matrix theory
for real symmetric matrix.
Step 5: realistic symmetrical matrix
proper vector
and eigenwert
, meet
, wherein
（
）（3）；
Matrix
orthogonal matrix, matrix
?
column element is exactly eigenwert
characteristic of correspondence vector.
Step 6: according to above-mentioned real symmetric matrix
proper vector
and eigenwert
, obtain the variance contribution ratio of each proper vector and the accumulative variance contribution ratio of front several proper vector, obtain the major component describing power of fan;
Step 7: calculate and describe the major component of power of fan: by eigenwert is descending, proper vector is sorted, front n the proper vector that accumulative variance contribution ratio is greater than 95% is major component;
Generally get the individual larger eigenwert of front p that accumulative variance contribution ratio reaches 85-95%
corresponding first, second ...,
individual proper vector is major component.
The variance contribution ratio of each proper vector is defined as:
（4）；
The accumulative variance contribution ratio of a front p proper vector is defined as:
（5）。
Step 8: descending by eigenwert, selects the major component with class discrimination degree successively, in each classification of major component with class discrimination degree, selects corresponding blower fan as mark post blower fan.
In step 8, need by eigenwert descending, check the class discrimination degree of each major component successively.Specifically comprise following two aspects:
On the one hand, first few items proper vector (i.e. major component) characterizes the distribution situation that wind electric field blower is exerted oneself to greatest extent, each component as proper vector is prosign, and what so this proper vector reflected is, and each blower fan of this wind energy turbine set exerts oneself that change is basically identical; If each component of a certain major component presents good class discrimination degree, then this proper vector represents wind energy turbine set each wind-powered electricity generation blower fan and show different characteristics in this projector space, therefore for ensureing the representativeness of mark post blower fan, 1-2 Fans should be selected in each classification as the mark post blower fan of this wind energy turbine set.
On the other hand, by front 3 characteristic vector pickup out drafting pattern 2 after descending sequence.Be not difficult find, comprising in first maximum proper vector of energy, the numerical value that each blower fan is corresponding is basically identical, therefore, is characterized on this projecting direction, each blower fan of wind energy turbine set exert oneself change basically identical.For second major component that bag energy time is many, each blower fan shows different numerical value, therefore, mark post blower fans should be divided by two components, zero is greater than for major component component, be less than zero-sum close to zero blower fan 1-2 platform all should be selected as mark post blower fan.
The wind energy turbine set mark post ventilator selection method based on principal component analysis (PCA) of the various embodiments described above of the present invention, will play directive function to the mark post of wind energy turbine set selection in the future blower fan.
Last it is noted that the foregoing is only the preferred embodiments of the present invention, be not limited to the present invention, although with reference to previous embodiment to invention has been detailed description, for a person skilled in the art, it still can be modified to the technical scheme described in foregoing embodiments, or carries out equivalent replacement to wherein portion of techniques feature.Within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (2)
1., based on a wind energy turbine set mark post ventilator selection method for principal component analysis (PCA), it is characterized in that, comprising:
The history power curve of every typhoon electric fan in a, acquisition wind energy turbine set;
B, history power curve based on typhoon electric fan every in wind energy turbine set, set up blower fan and to exert oneself matrix X
m × n:
M is wind energy turbine set inner blower number of units, and n is the power sample number of every Fans, x
ijrepresent actual the exerting oneself of the i-th Fans, a jth moment point;
C, exert oneself to blower fan matrix X
m × ncarry out the process of square graduation,
The covariance matrix of matrix after d, computing;
E, the eigenwert asking for covariance matrix and proper vector;
F, proper vector sorted by eigenwert is descending, getting the proper vector corresponding to eigenwert that accumulative variance contribution ratio reaches 85-95% is major component;
G, will have the foundation of major component as mark post ventilator selection of class discrimination degree, carry out mark post ventilator selection, described step c specifically comprises:
C1, data prediction, deduct Mean Matrix by matrix X and be processed into the flat matrix of square
Wherein,
C2, based on above-mentioned data prediction result, carry out covariance calculating, obtain real symmetric matrix S
m × m:
C3, realistic symmetrical matrix S
m × mproper vector V and eigenwert Λ, meet SV=Λ V, wherein
Matrix V is orthogonal matrix, and the jth column element of matrix V is exactly eigenvalue λ
jcharacteristic of correspondence vector;
C4, according to above-mentioned real symmetric matrix S
m × mproper vector V and eigenwert Λ, obtain the variance contribution ratio of each proper vector and the accumulative variance contribution ratio of front several proper vector, obtain describing the major component of power of fan,
In step c4, described in obtain the operation of major component describing power of fan, specifically comprise:
Get the individual larger eigenvalue λ of front p that accumulative variance contribution ratio reaches 85-95%
1, λ
2..., λ
pcorresponding the 1st, the 2nd ..., p (p≤m) individual proper vector is major component;
The variance contribution ratio of each proper vector is defined as:
The accumulative variance contribution ratio of a front p proper vector is defined as:
Described steps d specifically comprises:
Descending by eigenwert, select the major component with class discrimination degree successively, in each classification of major component with class discrimination degree, select corresponding blower fan as mark post blower fan.
2. the wind energy turbine set mark post ventilator selection method based on principal component analysis (PCA) according to claim 1, it is characterized in that, described descending by eigenwert, select the major component with class discrimination degree successively, in each classification of major component with class discrimination degree, select corresponding blower fan as mark post blower fan, specifically comprise:
Descending by eigenwert, check the class discrimination degree of each major component successively;
If each component of a certain major component presents good class discrimination degree, then 1-2 Fans should be selected in each classification as the mark post blower fan of this wind energy turbine set;
For second major component that bag energy time is many, each blower fan shows different numerical value, mark post blower fans should be divided by two components, zero is greater than for major component component, be less than zero-sum close to zero blower fan 1-2 platform all should be selected as mark post blower fan.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310168790.XA CN103268573B (en) | 2013-05-09 | 2013-05-09 | A kind of wind energy turbine set mark post ventilator selection method based on principal component analysis (PCA) |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310168790.XA CN103268573B (en) | 2013-05-09 | 2013-05-09 | A kind of wind energy turbine set mark post ventilator selection method based on principal component analysis (PCA) |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103268573A CN103268573A (en) | 2013-08-28 |
| CN103268573B true CN103268573B (en) | 2016-02-24 |
Family
ID=49012200
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310168790.XA Expired - Fee Related CN103268573B (en) | 2013-05-09 | 2013-05-09 | A kind of wind energy turbine set mark post ventilator selection method based on principal component analysis (PCA) |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103268573B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104112236B (en) * | 2014-05-29 | 2018-04-27 | 国家电网公司 | The computational methods of wind power plant generated output |
| CN104200001B (en) * | 2014-07-23 | 2017-09-22 | 清华大学 | The choosing method of mark post blower fan |
| CN105978041B (en) * | 2016-03-23 | 2019-06-18 | 三一重型能源装备有限公司 | A kind of wind power station active power control method configuring mark post blower |
| CN106447234A (en) * | 2016-10-26 | 2017-02-22 | 国网电力科学研究院武汉南瑞有限责任公司 | A wind power plant abandoned wind power assessment method based on a hierarchical clustering method |
| CN106780147A (en) * | 2016-12-29 | 2017-05-31 | 南京天谷电气科技有限公司 | A kind of wind-resources assessment anemometer tower addressing optimization device and method of facing area |
| CN106897771B (en) * | 2017-01-03 | 2020-03-06 | 国能日新科技股份有限公司 | New energy sample board machine selection method and system based on chaotic genetic algorithm |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102709939B (en) * | 2012-05-22 | 2014-04-30 | 中国电力科学研究院 | Active power control method of wind power station for improving power generation efficiency of wind power station |
-
2013
- 2013-05-09 CN CN201310168790.XA patent/CN103268573B/en not_active Expired - Fee Related
Non-Patent Citations (2)
| Title |
|---|
| 井巷通风网路解算及风机最优化选择;周庠等;《有色矿山 》;19810302;第35-页 * |
| 浅谈电网改造中配电变压器的选择;宋广涛等;《黑龙江科技信息》;20091215;第11页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103268573A (en) | 2013-08-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103268573B (en) | A kind of wind energy turbine set mark post ventilator selection method based on principal component analysis (PCA) | |
| Weng et al. | Laplacian Nelder-Mead spherical evolution for parameter estimation of photovoltaic models | |
| CN103268572B (en) | A kind of microcosmic structure method of ten million multikilowatt large-scale wind electricity base wind measurement network | |
| Vuong et al. | Modelling and simulation of BIPV/T in EnergyPlus and TRNSYS | |
| CN103020423A (en) | Copula-function-based method for acquiring relevant characteristic of wind power plant capacity | |
| CN104951834A (en) | LSSVM (least squares support vector machine) wind speed forecasting method based on integration of GA (genetic algorithm) and PSO (particle swarm optimization) | |
| CN103336995B (en) | The construction method of a kind of million kilowatt photovoltaic generation base light simultaneous measurement network | |
| CN105184683A (en) | Probability clustering method based on wind electric field operation data | |
| Trubiano et al. | Building simulation and evolutionary optimization in the conceptual design of a high-performance office building | |
| Nik et al. | Using typical and extreme weather files for impact assessment of climate change on buildings | |
| CN105447520A (en) | Sample classification method based on weighted PTSVM (projection twin support vector machine) | |
| CN105095989A (en) | Fourier-series-based fitting method of wind power probability distribution at same time | |
| CN106203734A (en) | A kind of photovoltaic plant capacity surpasses distribution coefficient computational methods | |
| CN113346489B (en) | New energy space coupling modeling evaluation method and system | |
| CN103294896B (en) | A kind of photovoltaic plant benchmark photovoltaic component system of selection based on principal component analysis | |
| Omer et al. | Adaptive boosting and bootstrapped aggregation based ensemble machine learning methods for photovoltaic systems output current prediction | |
| CN103870999A (en) | Rotated empirical orthogonal decomposition-based irradiance area division method | |
| CN104200001B (en) | The choosing method of mark post blower fan | |
| CN105095674A (en) | Distributed fan output correlation scenarios analysis method | |
| Huque et al. | Optimization of wind turbine airfoil using nondominated sorting genetic algorithm and pareto optimal front | |
| Su et al. | An evaluation of the effects of various parameter weights on typical meteorological years used for building energy simulation | |
| Rotas et al. | Dynamic simulation and performance enhancement analysis of a renewable driven trigeneration system | |
| CN115392101A (en) | Method and system for generating comprehensive energy random scene | |
| CN104933301A (en) | Calculation method for calculating available capacity of wind power plant | |
| MH | EFFICIENCY RANKING OF TURKISH WIND POWER PLANTS BY USING DATA ENVELOPMENT ANALYSIS AND TOPSIS. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160224 Termination date: 20190509 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |